All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=627867

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg8o7WrwkM


Bot(s) for this bug's original alert(s):

chromium-rel-win10

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9007236352132903760

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9007159803770727584

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9005150484921632928

=== Auto-CCing suspected CL author rbyers@chromium.org ===

Hi rbyers@chromium.org, the bisect results pointed to your CL below as possibly
causing a regression. Please have a look at this info and see whether
your CL be related.


===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : Revert of [perf] Enable non-verbose logging in memory system health benchmarks (patchset #3 id:60001 of https://codereview.chromium.org/2094143005/ )
Author  : rbyers
Commit description:
  
Reason for revert:
Seeing system_health.memory_desktop failures on Windows.  petrcermak@ says this CL is the likely culprit and should be reverted.

https://bugs.chromium.org/p/chromium/issues/detail?id=625172

Original issue's description:
> [perf] Enable non-verbose logging in memory system health benchmarks
>
> Rationale: To help triage flakes on the perf waterfall.
>
> BUG= 623058 
> CQ_EXTRA_TRYBOTS=tryserver.chromium.perf:android_s5_perf_cq;tryserver.chromium.perf:mac_retina_perf_cq
>
> Committed: https://crrev.com/a29030040dff42fe4dc0317d81f49bdaf80f1185
> Cr-Commit-Position: refs/heads/master@{#402784}

TBR=nednguyen@google.com,perezju@chromium.org,primiano@chromium.org,petrcermak@chromium.org
# Not skipping CQ checks because original CL landed more than 1 days ago.
BUG= 623058 

Review-Url: https://codereview.chromium.org/2124333002
Cr-Commit-Position: refs/heads/master@{#404174}
Commit  : 5f24850ea0b9b4b4a8573c97f11758507e22ebde
Date    : Thu Jul 07 17:47:27 2016


===== TESTED REVISIONS =====
Revision         Mean       Std Dev  N  Good?
chromium@404161  128031264  0.0      5  good
chromium@404169  128031264  0.0      5  good
chromium@404173  128031264  0.0      5  good
chromium@404174  192042128  0.0      5  bad    <--
chromium@404175  192042128  0.0      5  bad
chromium@404176  192042128  0.0      5  bad
chromium@404190  192042128  0.0      5  bad

Bisect job ran on: winx64_10_perf_bisect
Bug ID: 627867

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_search-memory:chrome:all_processes:reported_by_chrome:tracing:effective_size_avg/load_search_taobao
Relative Change: 50.00%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64_10_perf_bisect/builds/651
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9005150484921632928


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5838607848308736

| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Tests>AutoBisect.  Thank you!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004904722424838352

This is really strange. Perhaps an bug in the estimating the size of tracing? I started another bisect and cc'ed tracing owners.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004849655448879600

===== BISECT JOB RESULTS =====
Status: failed


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N  Good?
chromium@404161  34673901  104054   5  good
chromium@404168  34605736  77481.6  5  good
chromium@404172  34644600  96988.6  5  good
chromium@404173  34582916  89357.1  5  good
chromium@404174  42193032  64470.0  5  bad
chromium@404176  42286647  93607.2  5  bad
chromium@404190  42220204  54239.6  5  bad

Bisect job ran on: win_8_perf_bisect
Bug ID: 627867

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_social-memory:chrome:all_processes:reported_by_chrome:winheap:effective_size_avg/load_social_tumblr
Relative Change: 21.76%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_8_perf_bisect/builds/2103
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004904722424838352


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5891083758731264

| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Tests>AutoBisect.  Thank you!

Given that even winheap increased after disabling logging, I think that the most likely explanation is that the values had been lower due to the failures caused by logging ( issue 625172 ). This view is supported by the fact that a symmetric improvement happened when logging was enabled (r402785).

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004757720531032224

===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : Revert of [perf] Enable non-verbose logging in memory system health benchmarks (patchset #3 id:60001 of https://codereview.chromium.org/2094143005/ )
Author  : rbyers
Commit description:
  
Reason for revert:
Seeing system_health.memory_desktop failures on Windows.  petrcermak@ says this CL is the likely culprit and should be reverted.

https://bugs.chromium.org/p/chromium/issues/detail?id=625172

Original issue's description:
> [perf] Enable non-verbose logging in memory system health benchmarks
>
> Rationale: To help triage flakes on the perf waterfall.
>
> BUG= 623058 
> CQ_EXTRA_TRYBOTS=tryserver.chromium.perf:android_s5_perf_cq;tryserver.chromium.perf:mac_retina_perf_cq
>
> Committed: https://crrev.com/a29030040dff42fe4dc0317d81f49bdaf80f1185
> Cr-Commit-Position: refs/heads/master@{#402784}

TBR=nednguyen@google.com,perezju@chromium.org,primiano@chromium.org,petrcermak@chromium.org
# Not skipping CQ checks because original CL landed more than 1 days ago.
BUG= 623058 

Review-Url: https://codereview.chromium.org/2124333002
Cr-Commit-Position: refs/heads/master@{#404174}
Commit  : 5f24850ea0b9b4b4a8573c97f11758507e22ebde
Date    : Thu Jul 07 17:47:27 2016


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N  Good?
chromium@404161  34560742  32175.0  5  good
chromium@404168  34614878  99858.0  5  good
chromium@404172  34604677  90068.3  5  good
chromium@404173  34603944  83019.8  5  good
chromium@404174  42235518  38943.3  5  bad    <--
chromium@404176  42230733  40536.8  5  bad
chromium@404190  42202961  43191.8  5  bad

Bisect job ran on: win_8_perf_bisect
Bug ID: 627867

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_social-memory:chrome:all_processes:reported_by_chrome:winheap:effective_size_avg/load_social_tumblr
Relative Change: 22.11%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_8_perf_bisect/builds/2107
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004904722424838352


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5891083758731264

| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Tests>AutoBisect.  Thank you!